这个模型有较好的构图、衣服、手脚逻辑和光影。它有非常干净和中性的画风，这使得它可以搭配各种画风LoRA。查看我已经发布的画风LoRA:<a target="_blank" rel="ugc" href="https://civarchive.com/user/silvermoong/models">https://civarchive.com/user/silvermoong/models</a>This model has great backgrounds, cloth, limbs and lighting. It is designed to have a clean and neutral style to work with style LoRAs. You can find my style LoRAs here: <a target="_blank" rel="ugc" href="https://civarchive.com/user/silvermoong/models">https://civarchive.com/user/silvermoong/models</a>推荐负面/Suggested negative prompts: (worst quality, low quality:1.4)<h3 id="heading-40">重量级更新，手部修复，使用方法如下！！Hugh update: Introducing hand fix!! Read more for how to:</h3>使用方法/how to： <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/486ae898-a2cf-4e51-8a11-d9c450414e5e/width=525/486ae898-a2cf-4e51-8a11-d9c450414e5e.jpeg" />Handfix可以直接使用，也可以按照下面的方法配合使用。Handfix model can be used directly. Or use with the original one together:<ol><li>把基础模型切换成handfix版本 Switch to handfix checkpoint<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e9cbcf0a-0579-4ac0-acfd-4eba8cb6b88d/width=525/e9cbcf0a-0579-4ac0-acfd-4eba8cb6b88d.jpeg" /></li><li>在设置中把enable refiner设置为first pass Under settings: set enable refiner to first pass<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9fcb6681-da91-490f-a2d1-8b8d70b4df7b/width=525/9fcb6681-da91-490f-a2d1-8b8d70b4df7b.jpeg" /></li><li>把Hires.fix和refiner模型设置为正常版本，修改refiner切入时机 Set Hires.fix and refiner models to original one. Modify refiner switch at based your steps<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/21e34bf6-2ce2-49d6-a24d-3546fbac495f/width=525/21e34bf6-2ce2-49d6-a24d-3546fbac495f.jpeg" /></li></ol>基于基础28步，高修14步的效果/effect based on 28 steps+14Highres fix steps:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3a14a126-ca1e-4829-8081-6c670b214a7e/width=525/3a14a126-ca1e-4829-8081-6c670b214a7e.jpeg" /> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4cdb79e8-3d8c-488c-b486-cac842944226/width=525/4cdb79e8-3d8c-488c-b486-cac842944226.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/66f7138a-b1b6-44b9-8a96-3b9c117a31f1/width=525/66f7138a-b1b6-44b9-8a96-3b9c117a31f1.jpeg" /><hr />史诗级更新v1.2 -&gt; v1.3：<ol><li>增加更多细节的同时减少了污染</li><li>更好的背景，更好的背景，衣服，四肢逻辑</li><li>更好的光影效果</li><li>稍稍增加了对比度，画面看起来更加通透</li></ol>可以参考下面的对比图Huge improvements from v1.2 -&gt; v1.3:<ol><li>More details while reducing unwanted elements.</li><li>Improved background details, background, cloth, limbs logics.</li><li>Improved lighting and shadows</li><li>Slightly increased contrast for better "clarity".</li></ol>Check the compares below:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/267ec83c-7597-41a3-93ac-2feec872661c/width=525/267ec83c-7597-41a3-93ac-2feec872661c.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5773eb88-8a88-45bc-9948-8a55e096490c/width=525/5773eb88-8a88-45bc-9948-8a55e096490c.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b13854da-379d-4560-b358-9797ccd12a1d/width=525/b13854da-379d-4560-b358-9797ccd12a1d.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/75beada0-97fc-40f5-91ec-95b110b454ea/width=525/75beada0-97fc-40f5-91ec-95b110b454ea.jpeg" /><hr />这是我日常使用的融合模型。它有：<ol><li>非常好的光影</li><li>比较好的手部</li><li>简单的用色，在使用画风LoRA的时候不会冲突、产生杂乱的颜色</li><li>非常少的污染，尽量减少提示词中没有的物品</li></ol>我认为基础模型需要简单、少污染、会画各种概念。这样使用人物、画风LoRA的时候的可以更加好地还原。建议负面：(worst quality, low quality:1.4)This is my everyday use model. it is aimed to:<ol><li>Getting great light effects</li><li>Improving hands</li><li>Being simple in coloring, so that it won't conflicts with style LoRAs</li><li>Minimize objects that are not in prompts</li></ol>I believe a good model should be simple, accurate, knowing many concepts. These are keys to make other LoRAs work well.Suggested negative prompts:(worst quality, low quality:1.4)

SilvermoonMix Base model

silvermoonmixBase_v14.safetensors

v1.4

1.5+HandFix+GachaSplashA3

Files with SHA256: 33246a4b648ab2277be29b4923fd87d781912dac575b6f73872590b2c3c69c17